{"total":76,"rows":[{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190,"area":"alignment"},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2402.18091","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","created":"2024-02-28","cited_by_count":46,"area":"alignment"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2305.01918","title":"Improving Contrastive Learning of Sentence Embeddings from AI Feedback","created":"2023-05-03","cited_by_count":29,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"area":"alignment"},{"id":"2506.16447","title":"Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"area":"alignment"},{"id":"2310.16960","title":"Privately Aligning Language Models with Reinforcement Learning","created":"2023-10-25","cited_by_count":17,"area":"alignment"},{"id":"2403.08309","title":"HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback","created":"2024-03-13","cited_by_count":15,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"area":"alignment"},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12,"area":"alignment"},{"id":"2411.09947","title":"LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning","created":"2024-11-15","cited_by_count":10,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2402.18950","title":"PopALM: Popularity-Aligned Language Models for Social Media Trendy Response Prediction","created":"2024-02-29","cited_by_count":8,"area":"alignment"},{"id":"2307.10867","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","created":"2023-07-20","cited_by_count":7,"area":"alignment"},{"id":"2502.02945","title":"LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction","created":"2025-02-05","cited_by_count":7,"area":"alignment"},{"id":"2504.10208","title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2104.08765","title":"Improving Neural Model Performance through Natural Language Feedback on Their Explanations","created":"2021-04-18","cited_by_count":5,"area":"alignment"},{"id":"2309.08583","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","created":"2023-09-15","cited_by_count":5,"area":"alignment"},{"id":"2410.04503","title":"LRHP: Learning Representations for Human Preferences via Preference Pairs","created":"2024-10-06","cited_by_count":5,"area":"alignment"},{"id":"2411.02785","title":"Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment","created":"2024-11-05","cited_by_count":5,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2601.10532","title":"PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models","created":"2026-01-15","cited_by_count":5,"area":"alignment"},{"id":"2406.11581","title":"Style Transfer with Multi-iteration Preference Optimization","created":"2024-06-17","cited_by_count":4,"area":"alignment"},{"id":"2410.20305","title":"Accelerating Direct Preference Optimization with Prefix Sharing","created":"2024-10-27","cited_by_count":4,"area":"alignment"},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2509.13244","title":"Evaluating LLM Alignment on Personality Inference from Real-World Interview Data","created":"2025-09-16","cited_by_count":4,"area":"alignment"},{"id":"2406.09397","title":"Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms","created":"2024-06-13","cited_by_count":3,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2506.02479","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2601.05882","title":"An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift","created":"2026-01-09","cited_by_count":2,"area":"alignment"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2407.13221","title":"Multimodal Label Relevance Ranking via Reinforcement Learning","created":"2024-07-18","cited_by_count":1,"area":"alignment"},{"id":"2407.17546","title":"Exploring Domain Robust Lightweight Reward Models based on Router Mechanism","created":"2024-07-24","cited_by_count":1,"area":"alignment"},{"id":"2412.10529","title":"Solving the Inverse Alignment Problem for Efficient RLHF","created":"2024-12-13","cited_by_count":1,"area":"alignment"},{"id":"2412.17572","title":"Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor","created":"2024-12-23","cited_by_count":1,"area":"alignment"},{"id":"2504.18180","title":"Aligning Language Models for Icelandic Legal Text Summarization","created":"2025-04-25","cited_by_count":1,"area":"alignment"},{"id":"2508.20038","title":"Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks","created":"2025-08-27","cited_by_count":1,"area":"alignment"},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2510.19265","title":"Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2511.06942","title":"HLPD: Aligning LLMs to Human Language Preference for Machine-Revised Text Detection","created":"2025-11-10","cited_by_count":1,"area":"alignment"},{"id":"2601.05075","title":"SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment","created":"2026-01-08","cited_by_count":1,"area":"alignment"},{"id":"2311.00953","title":"Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation","created":"2023-11-02","cited_by_count":0,"area":"alignment"},{"id":"2502.11379","title":"CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models","created":"2025-02-17","cited_by_count":0,"area":"alignment"},{"id":"2502.17538","title":"Policy Learning with a Natural Language Action Space: A Causal Approach","created":"2025-02-24","cited_by_count":0,"area":"alignment"},{"id":"2505.02581","title":"Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem","created":"2025-05-05","cited_by_count":0,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2507.03069","title":"ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization","created":"2025-07-03","cited_by_count":0,"area":"alignment"},{"id":"2511.13548","title":"ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2602.05056","title":"Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.06424","title":"From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2605.17458","title":"ClaHF: A Human Feedback-inspired Reinforcement Learning Framework for Improving Classification Tasks","created":"2026-05-17","cited_by_count":0,"area":"alignment"},{"id":"2608.20374","title":"VA-DPO: Valence-Arousal Direct Preference Optimization for Controllable Emotion Generation in Language Models","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2609.07808","title":"You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs","created":"2026-09-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}